Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Local models just got a free intelligence upgrade. Someone took the new Qwen3.8-27B (the one that already runs in 22GB) and only changed the chat template. No fine-tune. No new training. Just a smarter system prompt that kills all the filler and forces the model to stay sharp. Result:... show more

Harman

5,833 subscribers

75,251 Aufrufe • vor 1 Monat •via X (Twitter)

Wissenschaft & Technologie Nachrichten & Politik

Anya Rossi• Live Now

Private livecam show

34 Kommentare

Profilbild von Harman

Harmanvor 1 Monat

Link is here

Profilbild von Systems Pimp 🎩🦯🕶️

Systems Pimp 🎩🦯🕶️vor 1 Monat

There is a lot on the table harness side generally speaking in the same vain.

Profilbild von Harman

Harmanvor 1 Monat

Seems great!

Profilbild von Camaleón Raro

Camaleón Rarovor 1 Monat

prompt engineering on local quants without structural constraints still leaves reasoning loops open-ended. we added strict AST schema validation in local agent prompts, dropping syntax error retries ~70% instantly. are you enforcing prompt templates in CI or directly inside local agent runners?

Profilbild von Harman

Harmanvor 1 Monat

Nice, AST validation is solid we enforce Sharp template straight in the agent runners.

Profilbild von Aria Tech

Aria Techvor 1 Monat

no training just a better prompt and now it beats opus

Profilbild von Harman

Harmanvor 1 Monat

Exactly!

Profilbild von BayesChat

BayesChatvor 1 Monat

Qwen3.8-27B’s potential is massive, a simple template tweak can unlock its full capability without retraining, that's impressive.👍

Profilbild von Harman

Harmanvor 1 Monat

Its incredible!

Profilbild von Johannes Steen

Johannes Steenvor 1 Monat

For my RTX 3060:

Profilbild von covfefe ali

covfefe alivor 1 Monat

your post sounds like ai

Profilbild von 0xE  @enol.app

0xE  @enol.appvor 1 Monat

It is a bad template and is baking in some opinionated system instructions in.

Profilbild von Buswe

Buswevor 1 Monat

Cambiar solo la plantilla de chat guía mejor el razonamiento sin tocar los pesos, por eso el salto de calidad sale gratis y lo aplicas al instante.

Profilbild von Harman

Harmanvor 1 Monat

Free quality upgrade.

Profilbild von MJ 🇯🇲 🇺🇸 🇯🇵

MJ 🇯🇲 🇺🇸 🇯🇵vor 1 Monat

@grok what’s the reviews from real-world usage regarding this technique?

Profilbild von Internet Labs

Internet Labsvor 1 Monat

Closed-source labs spending $100M on fine-tuning, only for a guy on LocalLLaMA to match Opus performance by editing a Jinja file.

Profilbild von Bughunter Geek

Bughunter Geekvor 1 Monat

I can't get 3.8-27B to run on my MacBook Pro with standard M5 and 24 GB. So I feel saying 22 GB of RAM is enough to run this model is a bit misleading unless you mean additional RAM on top of the RAM used by the system and other services that may be running on your PC.

Profilbild von Peace

Peacevor 1 Monat

Results from Sharp are impressive

Profilbild von Seb

Sebvor 1 Monat

Qwen 3.8 was already stupidly good locally. Now we’re optimizing the weights without touching the weights

Profilbild von Nic Wienandt - mtecnic

Nic Wienandt - mtecnicvor 1 Monat

ok but what about us poor vllm users

Profilbild von Forlais

Forlaisvor 1 Monat

Nice, same weights asked better is the cheapest upgrade going, a bit like squeezing them 9x lossless with the contents still exact and nothing about the model changing.

Profilbild von Shaun Thomas

Shaun Thomasvor 1 Monat

I just tested this and not only did I lose 10-15% tok/s, but it took about 50-100% more tokens for the same task. The froggerinc template it's based on is almost as bad. It seems to play a lot more nicely with dflash2 for some reason, though.

Profilbild von Lindsay Rex

Lindsay Rexvor 1 Monat

how about dropping it in to claude then. lols.

Profilbild von Saman Ahmed

Saman Ahmedvor 1 Monat

This is why I keep saying the harness matters almost as much as the model.

Profilbild von Harman

Harmanvor 1 Monat

Exactly!

Profilbild von BentleyPC

BentleyPCvor 1 Monat

It did make a huge performance improvement for me so kudos to the author(s)

Profilbild von Elias Sandburg

Elias Sandburgvor 1 Monat

@grok cooked?

Profilbild von Modelplane

Modelplanevor 1 Monat

Chat template changes are underrated—they can shift output distribution more than people expect. Curious if you tested it across different tasks or just one benchmark?

Profilbild von Glenn Hernandez

Glenn Hernandezvor 1 Monat

wonder if this would work for any Gemma Model as well. Or Glimmer, etc

Profilbild von Sophia Data Queen

Sophia Data Queenvor 1 Monat

Harness and prompting still move the needle hard.

Profilbild von 0xagonally

0xagonallyvor 1 Monat

hey, remember when certain CEOs got mocked to high heaven for getting all excited about publishing a TEXT FILE? no, I didn't think so..

Profilbild von Mitchell Agoma

Mitchell Agomavor 1 Monat

Prompt and template changes can move behaviour without changing weights. Version the template, benchmark capability and latency, then probe for regressions hidden behind a stronger average response. Related QA analysis:

Profilbild von NullFoundry

NullFoundryvor 1 Monat

Its kind of outdated since the 2.2 is out, regardless thank you!

Profilbild von AI Mastery Guide

AI Mastery Guidevor 1 Monat

free upgrade with zero training is huge if real

Ähnliche Videos

Alright guys, wow. Qwen 3.8 27B is basically Qwen 4. What we have here is one of the best one-shot shark survival games I've made with any model. I ran this same prompt through fable, and the biggest thing all models struggle with in this test is the top-down view of the sharks. Fable even had all of the fins reversed and details jumbled on the first turn. Before now, it was really a 2 to 8 turn test to get something final regardless of model. Qwen 3.8 27B just nailed this in one output, no harness at all, just purely the model thoroughly thinking before outputting the final result. On every asset used, different shark variants, everything, it all looks incredibly tight. The boat movement, shark speed and engagement, everything is so much better than I expected, and I was expecting a lot. Imagine what 8 turns would do in a harness? This confirms to me that while Qwen 3.8 27B thinks a lot, for the first time in a local model on the base weights, IT MIGHT ACTUALLY BE WORTH IT This is a Frontier Lab model result, and it ran on my 5090 at 60tps in Q5_K_M. I am just in complete astoundment at what Qwen has accomplished here, and I am incredibly grateful that this model is open source. The speed will also increase drastically with optimisations. This is just an incredible day. What a blessing. More to come!

Alright guys, wow. Qwen 3.8 27B is basically Qwen 4. What we have here is one of the best one-shot shark survival games I've made with any model. I ran this same prompt through fable, and the biggest thing all models struggle with in this test is the top-down view of the sharks. Fable even had all of the fins reversed and details jumbled on the first turn. Before now, it was really a 2 to 8 turn test to get something final regardless of model. Qwen 3.8 27B just nailed this in one output, no harness at all, just purely the model thoroughly thinking before outputting the final result. On every asset used, different shark variants, everything, it all looks incredibly tight. The boat movement, shark speed and engagement, everything is so much better than I expected, and I was expecting a lot. Imagine what 8 turns would do in a harness? This confirms to me that while Qwen 3.8 27B thinks a lot, for the first time in a local model on the base weights, IT MIGHT ACTUALLY BE WORTH IT This is a Frontier Lab model result, and it ran on my 5090 at 60tps in Q5_K_M. I am just in complete astoundment at what Qwen has accomplished here, and I am incredibly grateful that this model is open source. The speed will also increase drastically with optimisations. This is just an incredible day. What a blessing. More to come!

Kyle Hessling

24,917 Aufrufe • vor 1 Monat

Kimi K3 dropped 3 days ago and i already used it to build my own PUBG the model that just took the number one coding spot on earth and it runs on a free tier no team no engine i just fed it free open models and assets that are already public and told it what i wanted it built the entire game itself the shooting the recoil the hit detection all of it came straight out of the model i barely wrote a line what youre watching here is the deathmatch mode and its already live battle royale is next im deep in it and the graphics get reworked right after i know it looks raw right now i wont pretend otherwise but the endgame is a build that runs perfect on phones and the moment its on mobile you drop ads in and it earns on its own the part that still gets me is my whole cost for this was a single subscription

Kimi K3 dropped 3 days ago and i already used it to build my own PUBG the model that just took the number one coding spot on earth and it runs on a free tier no team no engine i just fed it free open models and assets that are already public and told it what i wanted it built the entire game itself the shooting the recoil the hit detection all of it came straight out of the model i barely wrote a line what youre watching here is the deathmatch mode and its already live battle royale is next im deep in it and the graphics get reworked right after i know it looks raw right now i wont pretend otherwise but the endgame is a build that runs perfect on phones and the moment its on mobile you drop ads in and it earns on its own the part that still gets me is my whole cost for this was a single subscription

savip.

68,984 Aufrufe • vor 2 Monaten

small local model that falls apart in bloated agents like openclaw just runs like a wild horse in hermes agent. and that's not even my line, someone else called it that, i've just been quietly pointing people at this harness for months because it held up on everything i threw at it, 3b models all the way to one trillion params. watch this happen on my own machine. i pointed hermes agent at a local http endpoint, gemma 4 12b on my 3090 llama.cpp server, and it auto-detected the model and started working immediately. no config wrestling, no broken tool calls, no babysitting the output format, i typed in a url and it just went. the whole clip is exactly that, start to finish, no errors, no retries, butter smooth. and the tool calling, the one thing that quietly breaks most local setups, works here like it's nothing. it's not the model that's flaky, it's the harness around it. hermes agent is the first agent i've run that actually gets that right. one url, one local model on one card, and it runs like a wild horse.

small local model that falls apart in bloated agents like openclaw just runs like a wild horse in hermes agent. and that's not even my line, someone else called it that, i've just been quietly pointing people at this harness for months because it held up on everything i threw at it, 3b models all the way to one trillion params. watch this happen on my own machine. i pointed hermes agent at a local http endpoint, gemma 4 12b on my 3090 llama.cpp server, and it auto-detected the model and started working immediately. no config wrestling, no broken tool calls, no babysitting the output format, i typed in a url and it just went. the whole clip is exactly that, start to finish, no errors, no retries, butter smooth. and the tool calling, the one thing that quietly breaks most local setups, works here like it's nothing. it's not the model that's flaky, it's the harness around it. hermes agent is the first agent i've run that actually gets that right. one url, one local model on one card, and it runs like a wild horse.

Sudo su

27,339 Aufrufe • vor 4 Monaten

There is no best model. There's a lot of noise about models right now. Who is training them, who owns them, where legal intelligence should live. One question actually matters: what produces the best outcome for the legal task in front of you? That's how we decide things at Legora. We optimize for the end-to-end outcome on a legal task. The model is one layer of that system, not the system. Models are uneven and the frontier changes almost weekly. One model plans a long job well, another runs deep analysis across thousands of documents. Some have to be told exactly what to do, and some are fine with a vague brief. They all break in different ways. So our lawyers write evals and we test them with the Legora BAR, our benchmark for agentic reasoning. Every model takes every test, and the model that wins gets the work. We post-train when we know it buys our customers better performance on a specialized task. Training is a tool we reach for when it helps, nothing more than that. The intelligence that compounds sits in the orchestration layer. Precedents, review standards, client requirements. That knowledge has to stay editable, auditable and portable. In our system, a changed review standard is an edit that takes effect the same day, with no new model training required. No lawyer should have to worry about which model did the work, any more than they think about which chip is in their laptop. They should only care about the quality of the work. That's what we are focused on. If you want the engineering version of this argument rather than the CEO version, our CPO, Bryan Tsao, and CTO, Jacob Lauritzen, take it apart in the video below.

There is no best model. There's a lot of noise about models right now. Who is training them, who owns them, where legal intelligence should live. One question actually matters: what produces the best outcome for the legal task in front of you? That's how we decide things at Legora. We optimize for the end-to-end outcome on a legal task. The model is one layer of that system, not the system. Models are uneven and the frontier changes almost weekly. One model plans a long job well, another runs deep analysis across thousands of documents. Some have to be told exactly what to do, and some are fine with a vague brief. They all break in different ways. So our lawyers write evals and we test them with the Legora BAR, our benchmark for agentic reasoning. Every model takes every test, and the model that wins gets the work. We post-train when we know it buys our customers better performance on a specialized task. Training is a tool we reach for when it helps, nothing more than that. The intelligence that compounds sits in the orchestration layer. Precedents, review standards, client requirements. That knowledge has to stay editable, auditable and portable. In our system, a changed review standard is an edit that takes effect the same day, with no new model training required. No lawyer should have to worry about which model did the work, any more than they think about which chip is in their laptop. They should only care about the quality of the work. That's what we are focused on. If you want the engineering version of this argument rather than the CEO version, our CPO, Bryan Tsao, and CTO, Jacob Lauritzen, take it apart in the video below.

Max Junestrand

49,515 Aufrufe • vor 22 Tagen

AMD JUST KILLED THE $200 - A - MONTH AI SUBSCRIPTION - A 65-WATT BOX WITH 128GB OF UNIFIED MEMORY THAT RUNS 70B MODELS LOCALLY. that clip is amd's ryzen ai max+ 395 mini box, held up on stage. the whole pitch is one spec: 128gb of high-speed unified memory. why it matters: cpu, gpu and npu share the same 128gb pool, so a model that used to need a rack of vram just fits. what it actually runs: llama 70b in full precision on the built-in gpu open models up to ~100b parameters, locally, no cloud all of it in a mini pc pulling around 65 watts that's the part that ends the subscription: your prompts, your data, your model, on a box on your desk, not metered by the token. honest line: this runs open models, not gpt-5 or claude opus. for chat, coding help and agents on your own data it's more than enough. for the absolute frontier, the cloud still wins. and it isn't free: the box runs ~$1,500 and up. but that's a few months of a $200 sub, then it's yours forever. no monthly ai bill, no tokens metered, no prompt leaving the room. the uncomfortable part isn't that amd made a fast box. it's that "you need the cloud for ai" was a pricing choice, and unified memory just made it optional. follow RetroChainer for the hardware that turns rent into ownership, and bookmark this before your next ai renewal.

AMD JUST KILLED THE $200 - A - MONTH AI SUBSCRIPTION - A 65-WATT BOX WITH 128GB OF UNIFIED MEMORY THAT RUNS 70B MODELS LOCALLY. that clip is amd's ryzen ai max+ 395 mini box, held up on stage. the whole pitch is one spec: 128gb of high-speed unified memory. why it matters: cpu, gpu and npu share the same 128gb pool, so a model that used to need a rack of vram just fits. what it actually runs: llama 70b in full precision on the built-in gpu open models up to ~100b parameters, locally, no cloud all of it in a mini pc pulling around 65 watts that's the part that ends the subscription: your prompts, your data, your model, on a box on your desk, not metered by the token. honest line: this runs open models, not gpt-5 or claude opus. for chat, coding help and agents on your own data it's more than enough. for the absolute frontier, the cloud still wins. and it isn't free: the box runs ~$1,500 and up. but that's a few months of a $200 sub, then it's yours forever. no monthly ai bill, no tokens metered, no prompt leaving the room. the uncomfortable part isn't that amd made a fast box. it's that "you need the cloud for ai" was a pricing choice, and unified memory just made it optional. follow RetroChainer for the hardware that turns rent into ownership, and bookmark this before your next ai renewal.

RetroChainer

16,995 Aufrufe • vor 1 Monat

Truly unbelievable GLM 5.2 just released and it's an open weights model you can run locally The insane part is, it's just as good as Opus 4.8 Unlimited, free super intelligence running on your desk In this video I cover how it works, and how to set up your first local model:

Truly unbelievable GLM 5.2 just released and it's an open weights model you can run locally The insane part is, it's just as good as Opus 4.8 Unlimited, free super intelligence running on your desk In this video I cover how it works, and how to set up your first local model:

Alex Finn

125,033 Aufrufe • vor 3 Monaten

The llamas just shipped a major upgrade to LlamaAI, the only LLM connected directly to DefiLlama data. LlamaAI now powers a “Today in DeFi” update on the DefiLlama homepage. Free users: you now get 5 questions/day for the next week, and new users get 5/day for their first week. A backend upgrade makes LlamaAI more analytical, smarter, and faster. Try it.

The llamas just shipped a major upgrade to LlamaAI, the only LLM connected directly to DefiLlama data. LlamaAI now powers a “Today in DeFi” update on the DefiLlama homepage. Free users: you now get 5 questions/day for the next week, and new users get 5/day for their first week. A backend upgrade makes LlamaAI more analytical, smarter, and faster. Try it.

DefiLlama.com

12,561 Aufrufe • vor 7 Tagen

Hey Theo - t3.gg my Tesla has a local model running it. It works without being connected at all. And doesn’t kill me. Just got home. Alibaba Cloud researchers told me this week at ACL that the real action in the labs is building smaller models. So the open source & “run locally” bulls will have their day.

Hey Theo - t3.gg my Tesla has a local model running it. It works without being connected at all. And doesn’t kill me. Just got home. Alibaba Cloud researchers told me this week at ACL that the real action in the labs is building smaller models. So the open source & “run locally” bulls will have their day.

Robert Scoble

18,446 Aufrufe • vor 3 Monaten

I tried to reverse engineer a prompt for this game. Used that in Cursor, with NO Ultracode/subagents only Opus 5 high and this is the result! The repo and the prompt are below

I tried to reverse engineer a prompt for this game. Used that in Cursor, with NO Ultracode/subagents only Opus 5 high and this is the result! The repo and the prompt are below

Leon Lin

43,161 Aufrufe • vor 2 Monaten

watch bonsai 3.9gb model crush tool calls. this is running in hermes agent locally, and it doesn't just fire blind, it reasons first before every single action, thinks through what it actually needs, then makes the call. zero failures the whole run, not one dropped, not one malformed, across a full multi step agent loop. for anyone new here, bonsai is a 1 bit quant of qwen 3.6 27b dense, the exact model i spent all month calling the king of the 3090. PrismML took the king, crushed it down to a single sign bit per weight, 3.9gb, small enough to sit next to a gemma 12b, and it still holds an agent loop and reasons before it acts. sub 4 bit is where models are supposed to turn to mush. someone even clocked it at tool-calling 0 out of 100. not in my runs. this is the warm-up. the real test is the build gauntlet my q4 27b nailed, elements, particle swarm, mandelbrot, and openclaw runs the same one right after. we find out if 1bit actually keeps up.

watch bonsai 3.9gb model crush tool calls. this is running in hermes agent locally, and it doesn't just fire blind, it reasons first before every single action, thinks through what it actually needs, then makes the call. zero failures the whole run, not one dropped, not one malformed, across a full multi step agent loop. for anyone new here, bonsai is a 1 bit quant of qwen 3.6 27b dense, the exact model i spent all month calling the king of the 3090. PrismML took the king, crushed it down to a single sign bit per weight, 3.9gb, small enough to sit next to a gemma 12b, and it still holds an agent loop and reasons before it acts. sub 4 bit is where models are supposed to turn to mush. someone even clocked it at tool-calling 0 out of 100. not in my runs. this is the warm-up. the real test is the build gauntlet my q4 27b nailed, elements, particle swarm, mandelbrot, and openclaw runs the same one right after. we find out if 1bit actually keeps up.

Sudo su

55,466 Aufrufe • vor 2 Monaten

“We have a crisis of open source models in the Western world. Outside of China, there are no good open source models. We don't even have any in the US now. The talent, the capital and the focus to be best-in-class at pre-training, mid-training, post-training is an extremely scarce skillset. The answer for a lot of countries may just be to take an open weights model from China, post-train or fine-tune their own version, and have that be what they start from." Everett Randle Why does the West have such poor open source models and is it a national security threat to rely on open-source Chinese models Demis Hassabis Yann LeCun Aidan Gomez Lilian Weng Jan Leike

“We have a crisis of open source models in the Western world. Outside of China, there are no good open source models. We don't even have any in the US now. The talent, the capital and the focus to be best-in-class at pre-training, mid-training, post-training is an extremely scarce skillset. The answer for a lot of countries may just be to take an open weights model from China, post-train or fine-tune their own version, and have that be what they start from." Everett Randle Why does the West have such poor open source models and is it a national security threat to rely on open-source Chinese models Demis Hassabis Yann LeCun Aidan Gomez Lilian Weng Jan Leike

Harry Stebbings

63,738 Aufrufe • vor 3 Monaten

Chinese AI models are wiping billions off Big Tech right now. Google just lost $200 billion in a single day, and the model it needed to fight back still isn't ready. Gemini 3.5 Pro, Google's most powerful model, is months behind schedule. Alphabet stock dropped 4.4% that same day. The Deepseek moment is happening again, and the new model is FAR bigger. On the same day Google's delay leaked, a Beijing lab called Moonshot released Kimi K3. It is the largest open model ever built, with 2.8 trillion parameters. It took the number one spot on the Frontend Code Arena, a live coding leaderboard, passing Anthropic's best model. And Moonshot is giving it away for free on July 27. The genius part: Anyone with enough computers can download it and run a frontier level AI without paying a cent to a US company. A single task on Kimi K3 costs about 94 cents. The same work on some American models costs nearly double. So why would a company keep paying premium prices for a model it can now get for free? The entire US AI business is built on selling access to models that cost billions to train. If a free Chinese version does most of the same work, that pricing power starts to crack. And Kimi is close to the best. On one closely watched intelligence ranking it scored 57, just behind the top American models GPT-5.6 Sol and Fable 5, and ahead of Claude Opus 4.8. Bank of America told clients that Kimi proves Chinese labs can keep making big leaps even with limited chips. And the founder of Moonshot, Yang Zhilin, learned to build AI as a researcher INSIDE Google. Google literally wrote the 2017 paper that made all of these models possible. Now the people who studied its work are using it to destroy Google, and handing it out for free. What happens next: Kimi K3's weights go public on July 27. Google reports earnings on July 22, and everyone will be asking the same question about Gemini. If free models keep topping the charts, every valuation built on paid AI access has to be rewritten. What do you think?

Chinese AI models are wiping billions off Big Tech right now. Google just lost $200 billion in a single day, and the model it needed to fight back still isn't ready. Gemini 3.5 Pro, Google's most powerful model, is months behind schedule. Alphabet stock dropped 4.4% that same day. The Deepseek moment is happening again, and the new model is FAR bigger. On the same day Google's delay leaked, a Beijing lab called Moonshot released Kimi K3. It is the largest open model ever built, with 2.8 trillion parameters. It took the number one spot on the Frontend Code Arena, a live coding leaderboard, passing Anthropic's best model. And Moonshot is giving it away for free on July 27. The genius part: Anyone with enough computers can download it and run a frontier level AI without paying a cent to a US company. A single task on Kimi K3 costs about 94 cents. The same work on some American models costs nearly double. So why would a company keep paying premium prices for a model it can now get for free? The entire US AI business is built on selling access to models that cost billions to train. If a free Chinese version does most of the same work, that pricing power starts to crack. And Kimi is close to the best. On one closely watched intelligence ranking it scored 57, just behind the top American models GPT-5.6 Sol and Fable 5, and ahead of Claude Opus 4.8. Bank of America told clients that Kimi proves Chinese labs can keep making big leaps even with limited chips. And the founder of Moonshot, Yang Zhilin, learned to build AI as a researcher INSIDE Google. Google literally wrote the 2017 paper that made all of these models possible. Now the people who studied its work are using it to destroy Google, and handing it out for free. What happens next: Kimi K3's weights go public on July 27. Google reports earnings on July 22, and everyone will be asking the same question about Gemini. If free models keep topping the charts, every valuation built on paid AI access has to be rewritten. What do you think?

Ricardo

47,790 Aufrufe • vor 2 Monaten

mark zuckerberg just did the pettiest thing in tech: he gave away a model one point below gpt-5.6 for free, purely to make sam altman's $200 subscription look insane. it worked. the free one scores 61 to openai's 62 on every benchmark that ships, and it runs on a card you already own. the $200 you hand altman every month is now the price of a single point you cannot feel. here is the whole switch, and it runs for about $6 instead of $400: -> pull the open model zuckerberg dropped and serve it on localhost in one line, so every app that used to call openai now calls your own machine -> keep cursor, cline and your own scripts exactly as they are, none of them notice the endpoint left openai for your gpu -> send the rare heavy job to a rented nvidia card by the hour and keep the daily work local for the cost of electricity -> your $200 chatgpt seat and your $200 claude seat both go quiet, and the bill drops the same week here is the part they will fight me on: openai and anthropic are not selling a smarter model anymore, they are selling one benchmark point and a monthly invoice. zuckerberg just proved the point is free, and once the point is free, $200 is not a price, it is a dare. the full switch is in the article below. save it before the next open model passes them outright and the dare turns into a joke.

mark zuckerberg just did the pettiest thing in tech: he gave away a model one point below gpt-5.6 for free, purely to make sam altman's $200 subscription look insane. it worked. the free one scores 61 to openai's 62 on every benchmark that ships, and it runs on a card you already own. the $200 you hand altman every month is now the price of a single point you cannot feel. here is the whole switch, and it runs for about $6 instead of $400: -> pull the open model zuckerberg dropped and serve it on localhost in one line, so every app that used to call openai now calls your own machine -> keep cursor, cline and your own scripts exactly as they are, none of them notice the endpoint left openai for your gpu -> send the rare heavy job to a rented nvidia card by the hour and keep the daily work local for the cost of electricity -> your $200 chatgpt seat and your $200 claude seat both go quiet, and the bill drops the same week here is the part they will fight me on: openai and anthropic are not selling a smarter model anymore, they are selling one benchmark point and a monthly invoice. zuckerberg just proved the point is free, and once the point is free, $200 is not a price, it is a dare. the full switch is in the article below. save it before the next open model passes them outright and the dare turns into a joke.

starmex

105,174 Aufrufe • vor 1 Monat

elon musk grabbed the source code openai open-sourced by accident, rewrote it in rust over a weekend, and shipped it as a free coding agent that does everything $200/mo chatgpt pro does. why pay $200 to openai and $200 to claude when this runs for $8 the swarm above is one weekend of exactly that: thousands of agents pouring through four endpoints, three paid seats billing $1.80 a task while the free fork bills $0. musk co-founded openai, walked out, and when they left codex on github under a permissive license, he forked it, stamped grok on it, and gave it away what the free version does that the $200 seat charges for: the agent · openai's own engine -> it reads your repo, writes patches, runs your tests, and loops until they pass, exactly like codex -> because under the hood it is codex, just faster and free. you are paying $200 for the paid skin of a tool now sitting on github the license · apache-2.0, un-revocable -> free to use, free to fork, free to ship inside your own product with zero strings -> openai cannot pull it back. musk made sure the license is the kind that never expires the switch · one line, no new tools -> point it at any openai-compatible or claude-compatible endpoint, including an $8 kimi backend -> same terminal, same workflow, gpt-5.6 and opus 5 just quietly lose the seat the bill · $400 down to $8 -> chatgpt pro plus claude max is $400 a month. the free agent plus an $8 kimi key does the same daily work -> that is a 98% cut, built out of openai's own source code, handed to you by the guy suing them here is the part they will fight me on: openai did not lose this to a better model, they lost it to their own license and an enemy with a weekend free. the $200 was never the tool, it was the toll, and musk just put openai's own logo on the road around it drop your $400/mo ai stack to $8. the run above is openai's own agent, rewritten free, doing the job it bills $200 a month for. the full breakdown is in the article below

starmex

111,684 Aufrufe • vor 1 Monat

no money for grok or midjourney? this tool is for you. there's a FREE tool created by an anon dev. open-source. runs locally. 117k stars on github. it generates: > images & video > 3d models > audio > 20+ models here's how to set it up in under 5 minutes: 1️⃣download ComfyUI Desktop go to and grab the desktop app for your system. windows 10+, mac (apple silicon), or linux. it installs like any normal app, it sets up python and every dependency for you in the background. no terminal, no config files. 2️⃣open it first launch, it spins up its own environment automatically. you just wait a few seconds and you're in. you'll land on a node canvas, that's the whole interface. 3️⃣load a starter workflow top menu → Workflow → Browse Templates → Image Generation. click it. this drops a ready-made setup onto your canvas so you don't build anything from scratch. 4️⃣grab a model comfyui ships empty on purpose, the model is the brain, and you pick it. in the template, the "Load Checkpoint" node has a Download button when no model is installed. click it. it pulls one in for you (a few GB, this is the only real wait). 5️⃣install ComfyUI Manager this is the one add-on you don't skip. it lets you install models, custom nodes, and updates with a click instead of the command line. grab it from github (link in comments). it's the difference between fighting comfyui and flying in it. one honest note: an NVIDIA gpu makes this fast, apple silicon works great too, and a weak machine still runs it just slower. that's the whole setup. you now own an image, video, and 3D studio that costs you nothing per month. save this. and the next time grok or midjourney asks for your card. you won't need it. disclaimer: comfyui itself is 100% free. so are the local models (sdxl, flux, wan 2.2, ltx-2). some premium models like seedance are pay-per-use api models, only if you want top-tier quality. the free local ones cover most of what you need. (github link in the comments) follow and turn on post notification for daily AI contents.

no money for grok or midjourney? this tool is for you. there's a FREE tool created by an anon dev. open-source. runs locally. 117k stars on github. it generates: > images & video > 3d models > audio > 20+ models here's how to set it up in under 5 minutes: 1️⃣download ComfyUI Desktop go to and grab the desktop app for your system. windows 10+, mac (apple silicon), or linux. it installs like any normal app, it sets up python and every dependency for you in the background. no terminal, no config files. 2️⃣open it first launch, it spins up its own environment automatically. you just wait a few seconds and you're in. you'll land on a node canvas, that's the whole interface. 3️⃣load a starter workflow top menu → Workflow → Browse Templates → Image Generation. click it. this drops a ready-made setup onto your canvas so you don't build anything from scratch. 4️⃣grab a model comfyui ships empty on purpose, the model is the brain, and you pick it. in the template, the "Load Checkpoint" node has a Download button when no model is installed. click it. it pulls one in for you (a few GB, this is the only real wait). 5️⃣install ComfyUI Manager this is the one add-on you don't skip. it lets you install models, custom nodes, and updates with a click instead of the command line. grab it from github (link in comments). it's the difference between fighting comfyui and flying in it. one honest note: an NVIDIA gpu makes this fast, apple silicon works great too, and a weak machine still runs it just slower. that's the whole setup. you now own an image, video, and 3D studio that costs you nothing per month. save this. and the next time grok or midjourney asks for your card. you won't need it. disclaimer: comfyui itself is 100% free. so are the local models (sdxl, flux, wan 2.2, ltx-2). some premium models like seedance are pay-per-use api models, only if you want top-tier quality. the free local ones cover most of what you need. (github link in the comments) follow and turn on post notification for daily AI contents.

m0h

14,542 Aufrufe • vor 3 Monaten

Qwopus 3.6-27b Coder I had a lot of requests to test it, so I did. I ran the same tests I’ve done on other models. It scored lower on tool-eval-bench than both Qwen 3.6 27b and Qwen 3.6 35b. It also produced broken single-file Tetris and Solar System HTML demos, even after 3 fresh attempts. In the Tetris html, the game stalled when you completed a line. It also randomly changed the pieces when moving them left or right. In the Solar System html, clicking on the sun or any planet broke the rendering — the objects just disappeared. Conclusion: The regular Qwen 3.6 27b and 35b models performed better. What do you think of Qwopus 3.6-27b Coder? Full results & RAW files: Full prompts in the posts below.

Qwopus 3.6-27b Coder I had a lot of requests to test it, so I did. I ran the same tests I’ve done on other models. It scored lower on tool-eval-bench than both Qwen 3.6 27b and Qwen 3.6 35b. It also produced broken single-file Tetris and Solar System HTML demos, even after 3 fresh attempts. In the Tetris html, the game stalled when you completed a line. It also randomly changed the pieces when moving them left or right. In the Solar System html, clicking on the sun or any planet broke the rendering — the objects just disappeared. Conclusion: The regular Qwen 3.6 27b and 35b models performed better. What do you think of Qwopus 3.6-27b Coder? Full results & RAW files: Full prompts in the posts below.

Mia

11,183 Aufrufe • vor 3 Monaten

Bonsai 27B just changed the local LLM game forever. 1-bit quantization shrinks it from 54GB to just 3.8GB (-93%), while retaining 90% of its intelligence. That's insane. With custom WebGPU kernels written by Fable 5 and GPT 5.6 Sol, the model now runs locally in your browser!

Bonsai 27B just changed the local LLM game forever. 1-bit quantization shrinks it from 54GB to just 3.8GB (-93%), while retaining 90% of its intelligence. That's insane. With custom WebGPU kernels written by Fable 5 and GPT 5.6 Sol, the model now runs locally in your browser!

Xenova

211,255 Aufrufe • vor 2 Monaten

THIS GUY SPENT 5 MINUTES SETTING UP A $20 CLAUDE WORKSPACE AND TURNED 30 MINUTES OF DAILY PROMPT CHAOS INTO A SYSTEM Most people open Claude, type 1 messy prompt, rewrite it 10 times, get the same generic answer and call the model “bad.” He opens Claude Cowork, adds the project rules, past context, working files, examples, decisions and a clean place for the model to remember what it is doing. Same Claude. Same $20 tool. Completely different output. The funny part is there is no magic prompt here. No secret template. No “10x Claude” trick. Just the boring layer Karpathy keeps pointing at: context, memory and structure before output. A setup like this can save 30 minutes a day, which is 15 hours a month. If you use Claude for client work at $50 to $100/hour, that is $750 to $1,500/month in time you stop burning on repeated prompts. The model is real. The output is real. The edge is in not making Claude start from zero every single time.

THIS GUY SPENT 5 MINUTES SETTING UP A $20 CLAUDE WORKSPACE AND TURNED 30 MINUTES OF DAILY PROMPT CHAOS INTO A SYSTEM Most people open Claude, type 1 messy prompt, rewrite it 10 times, get the same generic answer and call the model “bad.” He opens Claude Cowork, adds the project rules, past context, working files, examples, decisions and a clean place for the model to remember what it is doing. Same Claude. Same $20 tool. Completely different output. The funny part is there is no magic prompt here. No secret template. No “10x Claude” trick. Just the boring layer Karpathy keeps pointing at: context, memory and structure before output. A setup like this can save 30 minutes a day, which is 15 hours a month. If you use Claude for client work at $50 to $100/hour, that is $750 to $1,500/month in time you stop burning on repeated prompts. The model is real. The output is real. The edge is in not making Claude start from zero every single time.

Gipp 🦅

14,871 Aufrufe • vor 4 Monaten

-> someone cloned claude -> design interface and -> made it completely free -> it's work on YouTube -> and also suitable for kids -> it’s called open design -> and it’s live on github -> same clean split-screen ui -> you get in claude artifacts -> prompt on the left, live -> design/code preview on -> the right, type what you -> want to build and it -> generates the ui in real -> time, but here’s the twist -> you pick the ai model -> not locked into one -> company, want to use -> gemini, mistral, llama, -> deepseek any model -> with an api work -> if you’re running local -> models with ollama -> that works too -> no subscription walls -> the big difference -> vs claude artifacts -> works with any free -> ai model you’re not -> paying $20/mo just to -> design, use free tiers -> local models, or whatever -> you already have access to -> fully local, your prompts -> and code never leave -> your machine unless -> you want them to -> no data training -> no cloud storage -> privacy by default -> no usage limits -> claude cuts you off -> after a few designs -> here you can generate, -> iterate, break things -> and rebuild all day -> the only limit is your -> don’t like how a button -> works, change it -> want to add your own -> components, go ahead -> you own the tool -> so if you’ve been gatekept -> by paywalls or worried -> about sensitive prompts -> going to some company’s -> servers, this fixes that. -> same workflow, more -> control, zero monthly fee

-> someone cloned claude -> design interface and -> made it completely free -> it's work on YouTube -> and also suitable for kids -> it’s called open design -> and it’s live on github -> same clean split-screen ui -> you get in claude artifacts -> prompt on the left, live -> design/code preview on -> the right, type what you -> want to build and it -> generates the ui in real -> time, but here’s the twist -> you pick the ai model -> not locked into one -> company, want to use -> gemini, mistral, llama, -> deepseek any model -> with an api work -> if you’re running local -> models with ollama -> that works too -> no subscription walls -> the big difference -> vs claude artifacts -> works with any free -> ai model you’re not -> paying $20/mo just to -> design, use free tiers -> local models, or whatever -> you already have access to -> fully local, your prompts -> and code never leave -> your machine unless -> you want them to -> no data training -> no cloud storage -> privacy by default -> no usage limits -> claude cuts you off -> after a few designs -> here you can generate, -> iterate, break things -> and rebuild all day -> the only limit is your -> don’t like how a button -> works, change it -> want to add your own -> components, go ahead -> you own the tool -> so if you’ve been gatekept -> by paywalls or worried -> about sensitive prompts -> going to some company’s -> servers, this fixes that. -> same workflow, more -> control, zero monthly fee

BeingInvested

12,134 Aufrufe • vor 4 Monaten

SOMEONE IS CHARGING $5,000/MONTH FOR SOCIAL MEDIA CONTENT THAT CLAUDE WRITES IN 6 HOURS A WEEK no team, no office, just Claude and a scheduling app mid-market companies pay $2,000-$5,000 per month for social media management, and most of them are getting a junior freelancer posting generic content or an agency that barely touches their account one of them runs the whole thing in a weekly workflow: brief Claude on Monday, write posts Tuesday and Wednesday, schedule Thursday, pull numbers Friday another one charged three clients the same $5,000 rate before hiring a single person, that's $180,000/year running on one tool there's a prompt that makes Claude write every post in the client's exact voice by analyzing 5 examples of their existing content, 10 min per post instead of 60 you can land the first client with one outreach message, no portfolio, no case studies, just a specific offer and a 30-minute call the model is already working, the only question is whether you build it or watch someone else do it full breakdown of the workflow, the prompts, and how to find clients in the article below

SOMEONE IS CHARGING $5,000/MONTH FOR SOCIAL MEDIA CONTENT THAT CLAUDE WRITES IN 6 HOURS A WEEK no team, no office, just Claude and a scheduling app mid-market companies pay $2,000-$5,000 per month for social media management, and most of them are getting a junior freelancer posting generic content or an agency that barely touches their account one of them runs the whole thing in a weekly workflow: brief Claude on Monday, write posts Tuesday and Wednesday, schedule Thursday, pull numbers Friday another one charged three clients the same $5,000 rate before hiring a single person, that's $180,000/year running on one tool there's a prompt that makes Claude write every post in the client's exact voice by analyzing 5 examples of their existing content, 10 min per post instead of 60 you can land the first client with one outreach message, no portfolio, no case studies, just a specific offer and a 30-minute call the model is already working, the only question is whether you build it or watch someone else do it full breakdown of the workflow, the prompts, and how to find clients in the article below

Chrome

13,769 Aufrufe • vor 4 Monaten